CBAM: Convolutional Block Attention Module

ECCV 2018 · Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon ·

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS~COCO detection, and VOC~2007 detection datasets. Our experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Code

Add Remove Mark official

xmu-xiaoma666/External-Attention-py…

10,797

2,917

Jongchan/attention-module

1,979

HaloTrouvaille/YOLO-Multi-Backbones…

481

kobiso/CBAM-keras

355

See all 31 implementations

Tasks

Add Remove

General Classification

Image Classification

Datasets

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

1x1 Convolution • Average Pooling • Batch Normalization • Bottleneck Residual Block • CBAM • Channel Attention Module • Convolution • Dense Connections • Depthwise Convolution • Depthwise Separable Convolution • Dropout • Faster R-CNN • Global Average Pooling • Grouped Convolution • Kaiming Initialization • Max Pooling • MobileNetV1 • Pointwise Convolution • Random Horizontal Flip • Random Resized Crop • ReLU • Residual Block • Residual Connection • ResNet • ResNeXt • ResNeXt Block • RoIPool • RPN • SGD with Momentum • Sigmoid Activation • Softmax • Spatial Attention Module • Squeeze-and-Excitation Block • Step Decay • VGG • Weight Decay • Wide Residual Block • WideResNet